mirror of
https://github.com/deepseek-ai/DeepSeek-VL
synced 2024-11-21 19:07:40 +00:00
54 lines
1.6 KiB
Python
54 lines
1.6 KiB
Python
import torch
|
|
from transformers import AutoModelForCausalLM
|
|
|
|
from deepseek_vl.models import VLChatProcessor, MultiModalityCausalLM
|
|
from deepseek_vl.utils.io import load_pil_images
|
|
|
|
|
|
# specify the path to the model
|
|
model_path = "deepseek-ai/deepseek-vl-7b-chat"
|
|
vl_chat_processor: VLChatProcessor = VLChatProcessor.from_pretrained(model_path)
|
|
tokenizer = vl_chat_processor.tokenizer
|
|
|
|
vl_gpt: MultiModalityCausalLM = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True)
|
|
vl_gpt = vl_gpt.to(torch.bfloat16).cuda().eval()
|
|
|
|
conversation = [
|
|
{
|
|
"role": "User",
|
|
"content": "<image_placeholder>Describe each stage of this image.",
|
|
"images": ["./images/training_pipelines.jpg"]
|
|
},
|
|
{
|
|
"role": "Assistant",
|
|
"content": ""
|
|
}
|
|
]
|
|
|
|
|
|
# load images and prepare for inputs
|
|
pil_images = load_pil_images(conversation)
|
|
prepare_inputs = vl_chat_processor(
|
|
conversations=conversation,
|
|
images=pil_images,
|
|
force_batchify=True
|
|
).to(vl_gpt.device)
|
|
|
|
# run image encoder to get the image embeddings
|
|
inputs_embeds = vl_gpt.prepare_inputs_embeds(**prepare_inputs)
|
|
|
|
# run the model to get the response
|
|
outputs = vl_gpt.language_model.generate(
|
|
inputs_embeds=inputs_embeds,
|
|
attention_mask=prepare_inputs.attention_mask,
|
|
pad_token_id=tokenizer.eos_token_id,
|
|
bos_token_id=tokenizer.bos_token_id,
|
|
eos_token_id=tokenizer.eos_token_id,
|
|
max_new_tokens=512,
|
|
do_sample=False,
|
|
use_cache=True
|
|
)
|
|
|
|
answer = tokenizer.decode(outputs[0].cpu().tolist(), skip_special_tokens=True)
|
|
print(f"{prepare_inputs['sft_format'][0]}", answer)
|